Instructions to use E6E831728/fixed-minimal-binary-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use E6E831728/fixed-minimal-binary-code with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="E6E831728/fixed-minimal-binary-code", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("E6E831728/fixed-minimal-binary-code", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use E6E831728/fixed-minimal-binary-code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "E6E831728/fixed-minimal-binary-code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "E6E831728/fixed-minimal-binary-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/E6E831728/fixed-minimal-binary-code

SGLang

How to use E6E831728/fixed-minimal-binary-code with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "E6E831728/fixed-minimal-binary-code" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "E6E831728/fixed-minimal-binary-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "E6E831728/fixed-minimal-binary-code" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "E6E831728/fixed-minimal-binary-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use E6E831728/fixed-minimal-binary-code with Docker Model Runner:
```
docker model run hf.co/E6E831728/fixed-minimal-binary-code
```

fixed-minimal-binary-code / README.md

E6E831728

Update README.md

baf891e verified 8 days ago

2.35 kB

license: apache-2.0
library_name: transformers
tags:
  - causal-lm
  - text-generation
  - transformer
  - decoder-only
  - fixed-embeddings
  - binary-token-codes
  - research
language:
  - en

Fixed Minimal Binary Code Model

This is an anonymized research checkpoint for the paper:

Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes

Model variant

This repository contains the fixed minimal binary token-code model.

Instead of a trainable input embedding table, each token ID is represented by its exact minimal binary code.

For vocabulary size:

V = 65,536

the minimal injective binary code width is:

K = ceil(log2(V)) = 16

The 16-dimensional binary code is tiled to model width 1024.

The model therefore uses:

0 trainable input-embedding parameters

The output projection remains standard and trainable.

Architecture

decoder-only Transformer
vocabulary size: 65,536
model width: 1024
number of layers: 32
number of attention heads: 32
context length: 1024
rotary positional embeddings
GELU activations
untied trainable output projection

Loading example

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo_id = "E6E831728/fixed-minimal-binary-code"

tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True)
model.eval()

prompt = "Question: What is the capital of France?\nAnswer:"
input_ids = torch.tensor([tokenizer.encode(prompt)], dtype=torch.long)

with torch.no_grad():
    output_ids = model.generate(input_ids, max_new_tokens=3, do_sample=False)

print(tokenizer.decode(output_ids[0].tolist()))

Intended use

This checkpoint is provided for anonymous review and reproducibility of the paper's main claim: a trainable input embedding table is not necessary for useful language modeling in the studied regime.

Limitations

This model is a research checkpoint. It is not intended for deployment. It may produce incorrect, biased, unsafe, or nonsensical outputs.

Training data

The model was trained on the same FineWeb-Edu + Cosmopedia mixture used for the matched comparisons in the paper. Dataset terms and licenses are those of the original datasets.